Repository navigation
Conversation
Co-authored-by: Codex GPT-6 <codex@openai.com>
augustd
marked this pull request as ready for review
October 9, 2026 00:29
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Tag mode currently prints the complete generated prompt and extracted user request before invoking Claude, even with
show_full_output: false. Inline review comments include attached diff context, so a credential in the commented-on code can be copied into the Actions log without appearing in the comment body.Add
trace_prompt, defaulting tofalse. Only the exact valuetrueenables these two payload logs. Prompt files continue to be written for Claude in both cases;show_full_outputand GitHub Actions debug mode do not implicitly enable tracing. The input description and documentation explain the exposure risk when opting in.Validation: all 972 tests pass, including regression cases for omitted, empty, false, uppercase, numeric, and true tracing inputs. The regression uses synthetic credentials in review diff context and confirms prompt/request files remain intact. TypeScript, formatting of changed files, and action input/default/runtime mapping checks pass.